ipoib_main.c

h内核

	/*
	 * Check if our queue is stopped.  Since we have the LLTX bit
	 * set, we can't rely on netif_stop_queue() preventing our
	 * xmit function from being called with a full queue.
	 */
	if (unlikely(netif_queue_stopped(dev))) {
		spin_unlock_irqrestore(&priv->tx_lock, flags);
		return NETDEV_TX_BUSY;
	}

	if (skb->dst && skb->dst->neighbour) {
		if (unlikely(!*to_ipoib_neigh(skb->dst->neighbour))) {
			path_lookup(skb, dev);
			goto out;
		}

		neigh = *to_ipoib_neigh(skb->dst->neighbour);

		if (likely(neigh->ah)) {
			ipoib_send(dev, skb, neigh->ah,
				   be32_to_cpup((__be32 *) skb->dst->neighbour->ha));
			goto out;
		}

		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
			spin_lock(&priv->lock);
			__skb_queue_tail(&neigh->queue, skb);
			spin_unlock(&priv->lock);
		} else {
			++priv->stats.tx_dropped;
			dev_kfree_skb_any(skb);
		}
	} else {
		struct ipoib_pseudoheader *phdr =
			(struct ipoib_pseudoheader *) skb->data;
		skb_pull(skb, sizeof *phdr);

		if (phdr->hwaddr[4] == 0xff) {
			/* Add in the P_Key for multicast*/
			phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff;
			phdr->hwaddr[9] = priv->pkey & 0xff;

			ipoib_mcast_send(dev, (union ib_gid *) (phdr->hwaddr + 4), skb);
		} else {
			/* unicast GID -- should be ARP reply */

			if (be16_to_cpup((u16 *) skb->data) != ETH_P_ARP) {
				ipoib_warn(priv, "Unicast, no %s: type %04x, QPN %06x "
					   IPOIB_GID_FMT "\n",
					   skb->dst ? "neigh" : "dst",
					   be16_to_cpup((u16 *) skb->data),
					   be32_to_cpup((u32 *) phdr->hwaddr),
					   IPOIB_GID_ARG(*(union ib_gid *) (phdr->hwaddr + 4)));
				dev_kfree_skb_any(skb);
				++priv->stats.tx_dropped;
				goto out;
			}

			unicast_arp_send(skb, dev, phdr);
		}
	}

out:
	spin_unlock_irqrestore(&priv->tx_lock, flags);

	return NETDEV_TX_OK;
}

static struct net_device_stats *ipoib_get_stats(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	return &priv->stats;
}

static void ipoib_timeout(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	ipoib_warn(priv, "transmit timeout: latency %ld\n",
		   jiffies - dev->trans_start);
	/* XXX reset QP, etc. */
}

static int ipoib_hard_header(struct sk_buff *skb,
			     struct net_device *dev,
			     unsigned short type,
			     void *daddr, void *saddr, unsigned len)
{
	struct ipoib_header *header;

	header = (struct ipoib_header *) skb_push(skb, sizeof *header);

	header->proto = htons(type);
	header->reserved = 0;

	/*
	 * If we don't have a neighbour structure, stuff the
	 * destination address onto the front of the skb so we can
	 * figure out where to send the packet later.
	 */
	if (!skb->dst || !skb->dst->neighbour) {
		struct ipoib_pseudoheader *phdr =
			(struct ipoib_pseudoheader *) skb_push(skb, sizeof *phdr);
		memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
	}

	return 0;
}

static void ipoib_set_mcast_list(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	schedule_work(&priv->restart_task);
}

static void ipoib_neigh_destructor(struct neighbour *n)
{
	struct ipoib_neigh *neigh = *to_ipoib_neigh(n);
	struct ipoib_dev_priv *priv = netdev_priv(n->dev);
	unsigned long flags;

	ipoib_dbg(priv,
		  "neigh_destructor for %06x " IPOIB_GID_FMT "\n",
		  be32_to_cpup((__be32 *) n->ha),
		  IPOIB_GID_ARG(*((union ib_gid *) (n->ha + 4))));

	spin_lock_irqsave(&priv->lock, flags);

	if (neigh) {
		if (neigh->ah)
			ipoib_put_ah(neigh->ah);
		list_del(&neigh->list);
		*to_ipoib_neigh(n) = NULL;
		kfree(neigh);
	}

	spin_unlock_irqrestore(&priv->lock, flags);
}

static int ipoib_neigh_setup(struct neighbour *neigh)
{
	/*
	 * Is this kosher?  I can't find anybody in the kernel that
	 * sets neigh->destructor, so we should be able to set it here
	 * without trouble.
	 */
	neigh->ops->destructor = ipoib_neigh_destructor;

	return 0;
}

static int ipoib_neigh_setup_dev(struct net_device *dev, struct neigh_parms *parms)
{
	parms->neigh_setup = ipoib_neigh_setup;

	return 0;
}

int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	/* Allocate RX/TX "rings" to hold queued skbs */

	priv->rx_ring =	kmalloc(IPOIB_RX_RING_SIZE * sizeof (struct ipoib_buf),
				GFP_KERNEL);
	if (!priv->rx_ring) {
		printk(KERN_WARNING "%s: failed to allocate RX ring (%d entries)\n",
		       ca->name, IPOIB_RX_RING_SIZE);
		goto out;
	}
	memset(priv->rx_ring, 0,
	       IPOIB_RX_RING_SIZE * sizeof (struct ipoib_buf));

	priv->tx_ring = kmalloc(IPOIB_TX_RING_SIZE * sizeof (struct ipoib_buf),
				GFP_KERNEL);
	if (!priv->tx_ring) {
		printk(KERN_WARNING "%s: failed to allocate TX ring (%d entries)\n",
		       ca->name, IPOIB_TX_RING_SIZE);
		goto out_rx_ring_cleanup;
	}
	memset(priv->tx_ring, 0,
	       IPOIB_TX_RING_SIZE * sizeof (struct ipoib_buf));

	/* priv->tx_head & tx_tail are already 0 */

	if (ipoib_ib_dev_init(dev, ca, port))
		goto out_tx_ring_cleanup;

	return 0;

out_tx_ring_cleanup:
	kfree(priv->tx_ring);

out_rx_ring_cleanup:
	kfree(priv->rx_ring);

out:
	return -ENOMEM;
}

void ipoib_dev_cleanup(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev), *cpriv, *tcpriv;

	ipoib_delete_debug_file(dev);

	/* Delete any child interfaces first */
	list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) {
		unregister_netdev(cpriv->dev);
		ipoib_dev_cleanup(cpriv->dev);
		free_netdev(cpriv->dev);
	}

	ipoib_ib_dev_cleanup(dev);

	if (priv->rx_ring) {
		kfree(priv->rx_ring);
		priv->rx_ring = NULL;
	}

	if (priv->tx_ring) {
		kfree(priv->tx_ring);
		priv->tx_ring = NULL;
	}
}

static void ipoib_setup(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	dev->open 		 = ipoib_open;
	dev->stop 		 = ipoib_stop;
	dev->change_mtu 	 = ipoib_change_mtu;
	dev->hard_start_xmit 	 = ipoib_start_xmit;
	dev->get_stats 		 = ipoib_get_stats;
	dev->tx_timeout 	 = ipoib_timeout;
	dev->hard_header 	 = ipoib_hard_header;
	dev->set_multicast_list  = ipoib_set_mcast_list;
	dev->neigh_setup         = ipoib_neigh_setup_dev;

	dev->watchdog_timeo 	 = HZ;

	dev->rebuild_header 	 = NULL;
	dev->set_mac_address 	 = NULL;
	dev->header_cache_update = NULL;

	dev->flags              |= IFF_BROADCAST | IFF_MULTICAST;

	/*
	 * We add in INFINIBAND_ALEN to allow for the destination
	 * address "pseudoheader" for skbs without neighbour struct.
	 */
	dev->hard_header_len 	 = IPOIB_ENCAP_LEN + INFINIBAND_ALEN;
	dev->addr_len 		 = INFINIBAND_ALEN;
	dev->type 		 = ARPHRD_INFINIBAND;
	dev->tx_queue_len 	 = IPOIB_TX_RING_SIZE * 2;
	dev->features            = NETIF_F_VLAN_CHALLENGED | NETIF_F_LLTX;

	/* MTU will be reset when mcast join happens */
	dev->mtu 		 = IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN;
	priv->mcast_mtu 	 = priv->admin_mtu = dev->mtu;

	memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN);

	netif_carrier_off(dev);

	SET_MODULE_OWNER(dev);

	priv->dev = dev;

	spin_lock_init(&priv->lock);
	spin_lock_init(&priv->tx_lock);

	init_MUTEX(&priv->mcast_mutex);
	init_MUTEX(&priv->vlan_mutex);

	INIT_LIST_HEAD(&priv->path_list);
	INIT_LIST_HEAD(&priv->child_intfs);
	INIT_LIST_HEAD(&priv->dead_ahs);
	INIT_LIST_HEAD(&priv->multicast_list);

	INIT_WORK(&priv->pkey_task,    ipoib_pkey_poll,          priv->dev);
	INIT_WORK(&priv->mcast_task,   ipoib_mcast_join_task,    priv->dev);
	INIT_WORK(&priv->flush_task,   ipoib_ib_dev_flush,       priv->dev);
	INIT_WORK(&priv->restart_task, ipoib_mcast_restart_task, priv->dev);
	INIT_WORK(&priv->ah_reap_task, ipoib_reap_ah,            priv->dev);
}

struct ipoib_dev_priv *ipoib_intf_alloc(const char *name)
{
	struct net_device *dev;

	dev = alloc_netdev((int) sizeof (struct ipoib_dev_priv), name,
			   ipoib_setup);
	if (!dev)
		return NULL;

	return netdev_priv(dev);
}

static ssize_t show_pkey(struct class_device *cdev, char *buf)
{
	struct ipoib_dev_priv *priv =
		netdev_priv(container_of(cdev, struct net_device, class_dev));

	return sprintf(buf, "0x%04x\n", priv->pkey);
}
static CLASS_DEVICE_ATTR(pkey, S_IRUGO, show_pkey, NULL);

static ssize_t create_child(struct class_device *cdev,
			    const char *buf, size_t count)
{
	int pkey;
	int ret;

	if (sscanf(buf, "%i", &pkey) != 1)
		return -EINVAL;

	if (pkey < 0 || pkey > 0xffff)
		return -EINVAL;

	ret = ipoib_vlan_add(container_of(cdev, struct net_device, class_dev),
			     pkey);

	return ret ? ret : count;
}
static CLASS_DEVICE_ATTR(create_child, S_IWUGO, NULL, create_child);

static ssize_t delete_child(struct class_device *cdev,
			    const char *buf, size_t count)
{
	int pkey;
	int ret;

	if (sscanf(buf, "%i", &pkey) != 1)
		return -EINVAL;

	if (pkey < 0 || pkey > 0xffff)
		return -EINVAL;

	ret = ipoib_vlan_delete(container_of(cdev, struct net_device, class_dev),
				pkey);

	return ret ? ret : count;

}
static CLASS_DEVICE_ATTR(delete_child, S_IWUGO, NULL, delete_child);

int ipoib_add_pkey_attr(struct net_device *dev)
{
	return class_device_create_file(&dev->class_dev,
					&class_device_attr_pkey);
}

static struct net_device *ipoib_add_port(const char *format,
					 struct ib_device *hca, u8 port)
{
	struct ipoib_dev_priv *priv;
	int result = -ENOMEM;

	priv = ipoib_intf_alloc(format);
	if (!priv)
		goto alloc_mem_failed;

	SET_NETDEV_DEV(priv->dev, hca->dma_device);

	result = ib_query_pkey(hca, port, 0, &priv->pkey);
	if (result) {
		printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
		       hca->name, port, result);
		goto alloc_mem_failed;
	}

	priv->dev->broadcast[8] = priv->pkey >> 8;
	priv->dev->broadcast[9] = priv->pkey & 0xff;

	result = ib_query_gid(hca, port, 0, &priv->local_gid);
	if (result) {
		printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n",
		       hca->name, port, result);
		goto alloc_mem_failed;
	} else
		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));


	result = ipoib_dev_init(priv->dev, hca, port);
	if (result < 0) {
		printk(KERN_WARNING "%s: failed to initialize port %d (ret = %d)\n",
		       hca->name, port, result);
		goto device_init_failed;
	}

	INIT_IB_EVENT_HANDLER(&priv->event_handler,
			      priv->ca, ipoib_event);
	result = ib_register_event_handler(&priv->event_handler);
	if (result < 0) {
		printk(KERN_WARNING "%s: ib_register_event_handler failed for "
		       "port %d (ret = %d)\n",
		       hca->name, port, result);
		goto event_failed;
	}

	result = register_netdev(priv->dev);
	if (result) {
		printk(KERN_WARNING "%s: couldn't register ipoib port %d; error %d\n",
		       hca->name, port, result);
		goto register_failed;
	}

	if (ipoib_create_debug_file(priv->dev))
		goto debug_failed;

	if (ipoib_add_pkey_attr(priv->dev))
		goto sysfs_failed;
	if (class_device_create_file(&priv->dev->class_dev,
				     &class_device_attr_create_child))
		goto sysfs_failed;
	if (class_device_create_file(&priv->dev->class_dev,
				     &class_device_attr_delete_child))
		goto sysfs_failed;

	return priv->dev;

sysfs_failed:
	ipoib_delete_debug_file(priv->dev);

debug_failed:
	unregister_netdev(priv->dev);

register_failed:
	ib_unregister_event_handler(&priv->event_handler);

event_failed:
	ipoib_dev_cleanup(priv->dev);

device_init_failed:
	free_netdev(priv->dev);

alloc_mem_failed:
	return ERR_PTR(result);
}

static void ipoib_add_one(struct ib_device *device)
{
	struct list_head *dev_list;
	struct net_device *dev;
	struct ipoib_dev_priv *priv;
	int s, e, p;

	dev_list = kmalloc(sizeof *dev_list, GFP_KERNEL);
	if (!dev_list)
		return;

	INIT_LIST_HEAD(dev_list);

	if (device->node_type == IB_NODE_SWITCH) {
		s = 0;
		e = 0;
	} else {
		s = 1;
		e = device->phys_port_cnt;
	}

	for (p = s; p <= e; ++p) {
		dev = ipoib_add_port("ib%d", device, p);
		if (!IS_ERR(dev)) {
			priv = netdev_priv(dev);
			list_add_tail(&priv->list, dev_list);
		}
	}

	ib_set_client_data(device, &ipoib_client, dev_list);
}

static void ipoib_remove_one(struct ib_device *device)
{
	struct ipoib_dev_priv *priv, *tmp;
	struct list_head *dev_list;

	dev_list = ib_get_client_data(device, &ipoib_client);

	list_for_each_entry_safe(priv, tmp, dev_list, list) {
		ib_unregister_event_handler(&priv->event_handler);

		unregister_netdev(priv->dev);
		ipoib_dev_cleanup(priv->dev);
		free_netdev(priv->dev);
	}
}

static int __init ipoib_init_module(void)
{
	int ret;

	ret = ipoib_register_debugfs();
	if (ret)
		return ret;

	/*
	 * We create our own workqueue mainly because we want to be
	 * able to flush it when devices are being removed.  We can't
	 * use schedule_work()/flush_scheduled_work() because both
	 * unregister_netdev() and linkwatch_event take the rtnl lock,
	 * so flush_scheduled_work() can deadlock during device
	 * removal.
	 */
	ipoib_workqueue = create_singlethread_workqueue("ipoib");
	if (!ipoib_workqueue) {
		ret = -ENOMEM;
		goto err_fs;
	}

	ret = ib_register_client(&ipoib_client);
	if (ret)
		goto err_wq;

	return 0;

err_fs:
	ipoib_unregister_debugfs();

err_wq:
	destroy_workqueue(ipoib_workqueue);

	return ret;
}

static void __exit ipoib_cleanup_module(void)
{
	ipoib_unregister_debugfs();
	ib_unregister_client(&ipoib_client);
	destroy_workqueue(ipoib_workqueue);
}

module_init(ipoib_init_module);
module_exit(ipoib_cleanup_module);